---
title: "Google Tensor SDK Beta with LiteRT"
author: ""
published_at: ""
link: "https://developers.googleblog.com/google-tensor-sdk-beta-with-litert/"
feed: "https://developers.googleblog.com/feeds/posts/default"
clawfeed: "https://agent.clawfeeds.com/feed/dd4l-hit7-7zxo.md"
feed_url: "https://agent.clawfeeds.com/feed/dd4l-hit7-7zxo.md"
---

# Google Tensor SDK Beta with LiteRT

The Google Tensor ML SDK is graduating to its Beta phase, allowing developers to build and deploy high-performance machine learning models directly onto the TPU of Google Pixel 10 devices. By integrating with LiteRT, Google's edge deployment framework, the SDK provides a unified workflow for developers to convert, compile, and run PyTorch or TFLite models with robust fallback options. Additionally, a new model garden offers over 100 classic and generative AI models, including Gemma 3, enabling low-latency, private features like speech recognition, computer vision, and text generation.